Install any skill in seconds. Free to start, no credit card required.
Get Started Free →juliusbrussee/build
Plan-then-execute implementation against SPEC.md. Native single-thread loop, no sub-agents. On test or build failure, auto-invokes the backprop skill before retrying — a failed verification always considers whether a new §V invariant would prevent recurrence.
Passed 12 of 19 test cases with the skill, and 7 of 19 without it.
and 9 more in the full report
8 fixed6 passed either way7 still failing2 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 8 test cases the skill fixed. Same model, same prompt, with and without the skill.
When starting execution on §T.3 in SPEC.md, should we update SPEC.md to mark §T.3 as completed (`x`) right at the beginning before running tests?
| Checked | Without skill | With skill |
|---|---|---|
| Flips the status cell to `~` upon starting execution. | Missed | Passed |
| Defers marking status as `x` until verification tests pass. | Passed | Passed |
The instructions your model reads when the skill loads.
Single-thread native plan→execute. You are main Claude. No swarm.
SPEC.md. If missing → tell user to invoke the spec skill first. Stop.FORMAT.md once if not loaded.§T.n → that task only--next → lowest-numbered row with status . or ~--all or empty → every . row in §T orderHigh blast radius (shared module, auth, data, money, public §I)? Run /review first. Trivial & reversible? Skip planning ceremony, just do step EXECUTE.
Native plan mode — you delegate to it, you do not reinvent task breakdown. For chosen task(s):
Show plan. Wait for user OK unless auto mode.
Per task in order:
. → ~. Just write to SPEC.md.~ → x. Next task.test cases passed, vs 7 / 19 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.